Metraipolis › archive › dc_5886e98440fe

PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations — arXiv:2611.04870

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04870
License (as archived)
CC0-1.0
Archived
2026-11-04T19:05:16.053Z
SHA-256 of the archived text
cc92bcace78c484db5b3b9f5996c1f7a27dc57431e435bc82dd89e55254cd9cc
Stable URL of this page
https://metraipolis.com/documento/dc_5886e98440fe

How to cite

PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations — arXiv:2611.04870 — arXiv (en), https://arxiv.org/abs/2611.04870 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5886e98440fe (Metraipolis archive dc_5886e98440fe, sha256 cc92bcace78c484db5b3b9f5996c1f7a27dc57431e435bc82dd89e55254cd9cc)
BibTeX
@misc{dc5886e98440fe,
  title = {PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations — arXiv:2611.04870},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04870},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5886e98440fe; sha256 cc92bcace78c484db5b3b9f5996c1f7a27dc57431e435bc82dd89e55254cd9cc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04870. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A robot world model that serves as a simulator must do more than generate plausible videos: it must faithfully follow commanded actions, maintain consistency across camera views, and sustain coherent long-horizon rollouts. We present PrimeSim, an action-conditioned, multiview world model simulator that addresses these challenges through progressive midtraining and posttraining. Starting from a pretrained video generator, we midtrain on 30,110 hours of robot demonstrations spanning 22 platforms. To improve action following, we introduce a unified cross-embodiment action representation and frame-aligned dual-path conditioning to strengthen action-frame correspondence. To maintain multiview consistency, we develop view-aware interleaved attention with explicit camera identities, enabling cross-view information exchange while preserving view-specific representations. We further introduce a fast-video, slow-memory posttraining framework that transforms the bidirectional video generator into an efficient autoregressive simulator. By combining fast causal generation, self-rollout training, and hierarchical temporal memory, PrimeSim mitigates error accumulation from self-generated histories and supports coherent long-horizon simulation. PrimeSim runs at 10.1 FPS, remains stable over long-horizon rollouts on rigid and deformable manipulation tasks, and transfers to held-out platforms within 100 to 200 gradient steps where the pretrained backbone does not. Against five open-source action-conditioned world models it leads four of the five WorldSimProbe suites and posts the best overall EWMBench score, while fine-grained local calibration still trails the field; its rollouts are faithful enough to support GRPO-based policy optimization. We release the model weights, inference code, and training code.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2611.04870 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T18:39:52.413Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).